Information Technology_USA - USA_Product Architect
Real Soft, Inc.
Jacksonville, FL, USA
5/9/2026
Full time
Please strictly adhere to the following resume naming convention:
ALL CAPS, NO SPACES B/T UNDERSCORES
PTN_US_GBAMSREQID_CandidateBeelineID
i.e. PTN_US_9999999_SKIPJOHNSON0413
: MAX CONFIRMED- -
MSP Owner: Shilpa Bajpai
Location: Cleveland OH- 100% onsite from Day 1.
Duration: 6 months
skill id: 10631636
Role: AI Tech Architect
Experience Required: 8-10years
Skills: Digital: Python, Digital: Machine Learning, Digital: Artificial Intelligence (AI), Digital: Chatbots / Conversational Agents, AI Agents, AI & Gen AI - Products & Tools
Job Description
Role Summary
We are looking for a highly experienced AI Architect specializing in Python-based AI development, Large Language Models (LLMs), and the design of chatbots and voice bots. The ideal candidate will architect enterprise-grade conversational AI solutions, ensure robust LLM performance monitoring, and drive innovation in Generative AI systems.
Key Responsibilities
LLM & Conversational AI Architecture
• Architect scalable solutions using LLMs, ChatGPT-style models, and voice AI frameworks.
• Design and build chatbots and voice bots using Python, ASR (Automatic Speech Recognition), TTS (Text-to-Speech), and NLP/LLM pipelines.
• Create frameworks for conversational flows, prompt engineering, retrieval-augmented generation (RAG), and context management.
Solution Development
• Build end-to-end AI applications using Python, integrating with APIs, databases, and cloud-native services.
• Develop modular and reusable components for LLM inference, vector search, embeddings, and model orchestration.
• Integrate LLMs with enterprise systems (CRM, ticketing, case management, internal knowledge bases).
LLM Performance Monitoring & Optimization
• Implement monitoring systems for latency, hallucination rate, safety compliance, drift detection, prompt performance, and model quality.
• Set up continuous evaluation (CEVAL), feedback loops, and telemetry dashboards.
• Optimize inference cost, token usage, model selection (small vs. large models), and caching strategies
Voice Bot & Chat Bot Engineering
• Architect solutions using:
o Speech APIs (Azure Speech, Amazon Transcribe, Google Speech-to-Text)
o Chat platforms (Teams, Slack, web chat widgets)
o Telephony integrations (Twilio, Genesys, Ujet)
• Ensure high accuracy in intent detection, slot filling, sentiment tracking, and multimodal interaction.
MLOps & Deployment
• Implement MLOps practices including CI/CD, model versioning, A/B testing, evaluation pipelines, and governance.
• Deploy models on cloud platforms such as Azure, AWS, or GCP (Azure preferred if using OpenAI/Azure OpenAI).
Ensure compliance with enterprise AI governance, security, and ethical AI standards
Essential Skills: AI Architect| Python| LLM| Conversational AI Architecture| voice AI frameworks| ASR (Automatic Speech Recognition) | TTS (Text-to-Speech) | and NLPLLM pipelines| Voice Bot Chat Bot Engineering., Project Code :
ALL CAPS, NO SPACES B/T UNDERSCORES
PTN_US_GBAMSREQID_CandidateBeelineID
i.e. PTN_US_9999999_SKIPJOHNSON0413
: MAX CONFIRMED- -
MSP Owner: Shilpa Bajpai
Location: Cleveland OH- 100% onsite from Day 1.
Duration: 6 months
skill id: 10631636
Role: AI Tech Architect
Experience Required: 8-10years
Skills: Digital: Python, Digital: Machine Learning, Digital: Artificial Intelligence (AI), Digital: Chatbots / Conversational Agents, AI Agents, AI & Gen AI - Products & Tools
Job Description
Role Summary
We are looking for a highly experienced AI Architect specializing in Python-based AI development, Large Language Models (LLMs), and the design of chatbots and voice bots. The ideal candidate will architect enterprise-grade conversational AI solutions, ensure robust LLM performance monitoring, and drive innovation in Generative AI systems.
Key Responsibilities
LLM & Conversational AI Architecture
• Architect scalable solutions using LLMs, ChatGPT-style models, and voice AI frameworks.
• Design and build chatbots and voice bots using Python, ASR (Automatic Speech Recognition), TTS (Text-to-Speech), and NLP/LLM pipelines.
• Create frameworks for conversational flows, prompt engineering, retrieval-augmented generation (RAG), and context management.
Solution Development
• Build end-to-end AI applications using Python, integrating with APIs, databases, and cloud-native services.
• Develop modular and reusable components for LLM inference, vector search, embeddings, and model orchestration.
• Integrate LLMs with enterprise systems (CRM, ticketing, case management, internal knowledge bases).
LLM Performance Monitoring & Optimization
• Implement monitoring systems for latency, hallucination rate, safety compliance, drift detection, prompt performance, and model quality.
• Set up continuous evaluation (CEVAL), feedback loops, and telemetry dashboards.
• Optimize inference cost, token usage, model selection (small vs. large models), and caching strategies
Voice Bot & Chat Bot Engineering
• Architect solutions using:
o Speech APIs (Azure Speech, Amazon Transcribe, Google Speech-to-Text)
o Chat platforms (Teams, Slack, web chat widgets)
o Telephony integrations (Twilio, Genesys, Ujet)
• Ensure high accuracy in intent detection, slot filling, sentiment tracking, and multimodal interaction.
MLOps & Deployment
• Implement MLOps practices including CI/CD, model versioning, A/B testing, evaluation pipelines, and governance.
• Deploy models on cloud platforms such as Azure, AWS, or GCP (Azure preferred if using OpenAI/Azure OpenAI).
Ensure compliance with enterprise AI governance, security, and ethical AI standards
Essential Skills: AI Architect| Python| LLM| Conversational AI Architecture| voice AI frameworks| ASR (Automatic Speech Recognition) | TTS (Text-to-Speech) | and NLPLLM pipelines| Voice Bot Chat Bot Engineering., Project Code :